Keras載入mnist數(shù)據(jù)集出錯(cuò)問題解決方案

*
找到本地keras目錄下的mnist.py文件
通常在這個(gè)目錄下。
..\Anaconda3\Lib\site-packages\keras\datasets

*
下載mnist.npz文件到本地
下載鏈接如下。
https://pan.baidu.com/s/1C3c2Vn-_616GqeEn7hQQ2Q
<https://pan.baidu.com/s/1C3c2Vn-_616GqeEn7hQQ2Q>

*
修改mnist.py文件為以下內(nèi)容，并保存
from __future__ import absolute_import from __future__ import division from
__future__ import print_function from ..utils.data_utils import get_file import
numpy as np #cui 2018.07.08,修改 def load_data(path='mnist.npz'): """Loads the
MNIST dataset. # Arguments path: path where to cache the dataset locally
(relative to ~/.keras/datasets). # Returns Tuple of Numpy arrays: `(x_train,
y_train), (x_test, y_test)`. """ path = 'E:/Data/Mnist/mnist.npz'
#此處的path為你剛剛防止mnist.py的目錄。注意斜杠 f = np.load(path) x_train, y_train =
f['x_train'], f['y_train'] x_test, y_test = f['x_test'], f['y_test'] f.close()
return (x_train, y_train), (x_test, y_test)
** OK，去盡請(qǐng)使用吧 **

• ? 上一篇：100天搞定機(jī)器學(xué)習(xí)|day39 Tensorflow Keras手寫數(shù)字識(shí)別
• ? 下一篇：【程序人生】從湖北省最早的四位java高級(jí)工程師之一到出家為僧所引發(fā)的深思